AI agents call memento_autonomy_decisions to retrieve information from Memento without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only auditing tool that retrieves historical decision logs from the autonomous agent. While the server manages persistent memory and goal enforcement, this specific tool only accesses and returns existing data for review purposes. The deprecated status further suggests it is passive observation functionality. No data is created, modified, deleted, or financial operations are involved.
From the tool's definition Tool name contains 'decisions' and description explicitly states 'Get the full decision log' which is a retrieval operation. The verb 'Get' indicates reading/querying data without modification or side effects.
Attacks that exploit this kind of access
[DEPRECATED] Get the full decision log of the autonomous agent for auditing. It is categorised as a Read tool in the Memento MCP Server, which means it retrieves data without modifying state.
Register the Memento MCP server in PolicyLayer and add a rule for memento_autonomy_decisions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Memento. Nothing to install.
memento_autonomy_decisions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the memento_autonomy_decisions rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for memento_autonomy_decisions. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
memento_autonomy_decisions is provided by the Memento MCP server (joyciakira/memento). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →